{ "data_id": "39656", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3905", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3905", "version": 12, "version_label": null, "description": "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3905 (TID: 11842), and it has 919 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.", "format": "ARFF", "uploader": "Noureddin Sadawi", "uploader_id": 62, "visibility": "public", "creator": "\"Dr Jeremy Besnard, Dr Ivan Olier, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn\"", "contributor": null, "date": "2016-07-16 08:43:56", "update_comment": null, "last_update": "2016-07-16 08:43:56", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3680233\/data_53548.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3905", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3905 (TID: 11842), and it has 919 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 919, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.07725788900979326, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.036879770671551126, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.005561290803668752, "Quartile2MeansOfNumericAtts": 5.76435745375408, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 932.403899255977, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.028656507815300238, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.5596035188131836, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 0.702740208957322, "MaxKurtosisOfNumericAtts": 5.956176711788981, "MinMeansOfNumericAtts": 0.14951360174102285, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 39011.98585418932, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.9631079140580956, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MeansOfNumericAtts": 30.18690315560391, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -1.5089752756000854, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.796099773592952, "MinStdDevOfNumericAtts": 0.036809696967320525, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.41221616261429783, "MaxStdDevOfNumericAtts": 25770.095484405916, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.15626203752259937, "Quartile3StdDevOfNumericAtts": 15.063174171794726, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 1.9497323177366703, "StdvNominalAttDistinctValues": null, "MeanKurtosisOfNumericAtts": 0.6244171083622551, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 1384.1886187781745, "Quartile1SkewnessOfNumericAtts": -0.5254286160232833, "AutoCorrelation": 0.19730501089324728, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.31150789876384993 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "237", "missing": "0", "target": "1", "min": "4", "max": "10", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "919", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Eig07_AEA.bo.", "index": "1", "type": "numeric", "distinct": "546", "missing": "0", "min": "1", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Eig09_AEA.dm.", "index": "2", "type": "numeric", "distinct": "584", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "0" }, { "name": "Chi0_EA.dm.", "index": "3", "type": "numeric", "distinct": "777", "missing": "0", "min": "0", "max": "48", "mean": "21", "stdev": "9" }, { "name": "Eta_betaP", "index": "4", "type": "numeric", "distinct": "54", "missing": "0", "min": "8", "max": "36", "mean": "21", "stdev": "5" }, { "name": "Eta_FL", "index": "5", "type": "numeric", "distinct": "800", "missing": "0", "min": "3", "max": "14", "mean": "8", "stdev": "2" }, { "name": "Eig06_EA", "index": "6", "type": "numeric", "distinct": "554", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "SM14_AEA.bo.", "index": "7", "type": "numeric", "distinct": "554", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "ATS1m", "index": "8", "type": "numeric", "distinct": "552", "missing": "0", "min": "3", "max": "4", "mean": "4", "stdev": "0" }, { "name": "XMOD", "index": "9", "type": "numeric", "distinct": "851", "missing": "0", "min": "48", "max": "162", "mean": "93", "stdev": "21" }, { "name": "Eig09_EA.ri.", "index": "10", "type": "numeric", "distinct": "549", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig07_AEA.dm.", "index": "11", "type": "numeric", "distinct": "602", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" }, { "name": "MW", "index": "12", "type": "numeric", "distinct": "782", "missing": "0", "min": "211", "max": "747", "mean": "413", "stdev": "93" }, { "name": "Eig07_EA.ri.", "index": "13", "type": "numeric", "distinct": "605", "missing": "0", "min": "0", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "14", "type": "numeric", "distinct": "804", "missing": "0", "min": "0", "max": "77", "mean": "28", "stdev": "15" }, { "name": "Eig06_AEA.ri.", "index": "15", "type": "numeric", "distinct": "616", "missing": "0", "min": "2", "max": "4", "mean": "3", "stdev": "0" }, { "name": "UNIP", "index": "16", "type": "numeric", "distinct": "220", "missing": "0", "min": "32", "max": "469", "mean": "129", "stdev": "57" }, { "name": "IDET", "index": "17", "type": "numeric", "distinct": "804", "missing": "0", "min": "259", "max": "6666", "mean": "1702", "stdev": "943" }, { "name": "Xu", "index": "18", "type": "numeric", "distinct": "794", "missing": "0", "min": "14", "max": "47", "mean": "28", "stdev": "6" }, { "name": "P_VSA_m_2", "index": "19", "type": "numeric", "distinct": "831", "missing": "0", "min": "71", "max": "620", "mean": "211", "stdev": "54" }, { "name": "LPRS", "index": "20", "type": "numeric", "distinct": "807", "missing": "0", "min": "56", "max": "346", "mean": "154", "stdev": "49" }, { "name": "IDMT", "index": "21", "type": "numeric", "distinct": "805", "missing": "0", "min": "2088", "max": "170260", "mean": "25940", "stdev": "19546" }, { "name": "SM04_EA.bo.", "index": "22", "type": "numeric", "distinct": "526", "missing": "0", "min": "6", "max": "8", "mean": "7", "stdev": "0" }, { "name": "IDDM", "index": "23", "type": "numeric", "distinct": "345", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SMTI", "index": "24", "type": "numeric", "distinct": "799", "missing": "0", "min": "1392", "max": "66728", "mean": "12837", "stdev": "8578" }, { "name": "Eig10_EA.bo.", "index": "25", "type": "numeric", "distinct": "549", "missing": "0", "min": "-1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "SpMax8_Bh.v.", "index": "26", "type": "numeric", "distinct": "458", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "SM04_AEA.bo.", "index": "27", "type": "numeric", "distinct": "507", "missing": "0", "min": "7", "max": "8", "mean": "8", "stdev": "0" }, { "name": "GMTI", "index": "28", "type": "numeric", "distinct": "794", "missing": "0", "min": "1269", "max": "65963", "mean": "13566", "stdev": "9209" }, { "name": "Eig15_AEA.dm.", "index": "29", "type": "numeric", "distinct": "620", "missing": "0", "min": "-2", "max": "2", "mean": "0", "stdev": "1" }, { "name": "VvdwZAZ", "index": "30", "type": "numeric", "distinct": "811", "missing": "0", "min": "146", "max": "711", "mean": "351", "stdev": "87" }, { "name": "IDE", "index": "31", "type": "numeric", "distinct": "594", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Ui", "index": "32", "type": "numeric", "distinct": "29", "missing": "0", "min": "2", "max": "4", "mean": "4", "stdev": "0" }, { "name": "MSD", "index": "33", "type": "numeric", "distinct": "744", "missing": "0", "min": "3", "max": "14", "mean": "7", "stdev": "2" }, { "name": "SpMax8_Bh.p.", "index": "34", "type": "numeric", "distinct": "450", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "0" }, { "name": "S1K", "index": "35", "type": "numeric", "distinct": "685", "missing": "0", "min": "9", "max": "45", "mean": "20", "stdev": "5" }, { "name": "CSI", "index": "36", "type": "numeric", "distinct": "580", "missing": "0", "min": "154", "max": "2406", "mean": "797", "stdev": "367" }, { "name": "ECC", "index": "37", "type": "numeric", "distinct": "433", "missing": "0", "min": "76", "max": "1198", "mean": "367", "stdev": "168" }, { "name": "nSK", "index": "38", "type": "numeric", "distinct": "36", "missing": "0", "min": "15", "max": "54", "mean": "30", "stdev": "7" }, { "name": "nBM", "index": "39", "type": "numeric", "distinct": "29", "missing": "0", "min": "6", "max": "35", "mean": "21", "stdev": "5" }, { "name": "Uc", "index": "40", "type": "numeric", "distinct": "29", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "SpAD_EA.ed.", "index": "41", "type": "numeric", "distinct": "804", "missing": "0", "min": "62", "max": "274", "mean": "144", "stdev": "36" }, { "name": "ZM2Per", "index": "42", "type": "numeric", "distinct": "874", "missing": "0", "min": "292", "max": "1259", "mean": "717", "stdev": "169" }, { "name": "SpMaxA_AEA.bo.", "index": "43", "type": "numeric", "distinct": "165", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Eig12_EA.bo.", "index": "44", "type": "numeric", "distinct": "573", "missing": "0", "min": "-2", "max": "3", "mean": "1", "stdev": "1" }, { "name": "Eig11_AEA.dm.", "index": "45", "type": "numeric", "distinct": "542", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SpMax5_Bh.m.", "index": "46", "type": "numeric", "distinct": "522", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Dz", "index": "47", "type": "numeric", "distinct": "265", "missing": "0", "min": "32", "max": "120", "mean": "65", "stdev": "15" }, { "name": "DECC", "index": "48", "type": "numeric", "distinct": "620", "missing": "0", "min": "1", "max": "4", "mean": "2", "stdev": "1" }, { "name": "GMTIV", "index": "49", "type": "numeric", "distinct": "882", "missing": "0", "min": "4937", "max": "207751", "mean": "39012", "stdev": "25770" }, { "name": "SM02_AEA.ed.", "index": "50", "type": "numeric", "distinct": "196", "missing": "0", "min": "5", "max": "7", "mean": "6", "stdev": "0" }, { "name": "ATSC5m", "index": "51", "type": "numeric", "distinct": "899", "missing": "0", "min": "4", "max": "82", "mean": "28", "stdev": "11" }, { "name": "ON0", "index": "52", "type": "numeric", "distinct": "166", "missing": "0", "min": "8", "max": "31", "mean": "15", "stdev": "4" }, { "name": "MDDD", "index": "53", "type": "numeric", "distinct": "781", "missing": "0", "min": "7", "max": "95", "mean": "32", "stdev": "15" }, { "name": "ATS1s", "index": "54", "type": "numeric", "distinct": "557", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "Vindex", "index": "55", "type": "numeric", "distinct": "206", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GGI9", "index": "56", "type": "numeric", "distinct": "349", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMax5_Bh.e.", "index": "57", "type": "numeric", "distinct": "489", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "Psi_e_1", "index": "58", "type": "numeric", "distinct": "795", "missing": "0", "min": "2", "max": "9", "mean": "5", "stdev": "1" }, { "name": "SpMin6_Bh.v.", "index": "59", "type": "numeric", "distinct": "441", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "Eig12_AEA.dm.", "index": "60", "type": "numeric", "distinct": "554", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "piPC04", "index": "61", "type": "numeric", "distinct": "538", "missing": "0", "min": "4", "max": "7", "mean": "6", "stdev": "0" }, { "name": "MPC05", "index": "62", "type": "numeric", "distinct": "140", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "SM03_AEA.ed.", "index": "63", "type": "numeric", "distinct": "507", "missing": "0", "min": "7", "max": "8", "mean": "7", "stdev": "0" }, { "name": "Eig12_EA", "index": "64", "type": "numeric", "distinct": "520", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SM06_AEA.dm.", "index": "65", "type": "numeric", "distinct": "520", "missing": "0", "min": "-1", "max": "2", "mean": "1", "stdev": "1" }, { "name": "SRW10", "index": "66", "type": "numeric", "distinct": "545", "missing": "0", "min": "9", "max": "11", "mean": "10", "stdev": "0" }, { "name": "Ram", "index": "67", "type": "numeric", "distinct": "19", "missing": "0", "min": "3", "max": "22", "mean": "10", "stdev": "3" }, { "name": "ATSC4i", "index": "68", "type": "numeric", "distinct": "702", "missing": "0", "min": "0", "max": "3", "mean": "2", "stdev": "1" }, { "name": "Eig06_AEA.dm.", "index": "69", "type": "numeric", "distinct": "605", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }